File: TranscriptSequence.cpp

package info (click to toggle)
bitseq 0.7.5+dfsg-5
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 676 kB
  • sloc: cpp: 7,043; python: 562; makefile: 150; sh: 52
file content (197 lines) | stat: -rw-r--r-- 6,181 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
#include<algorithm>
#include<fstream>
#include<set>
#include<sstream>

#include "TranscriptSequence.h"

#include "misc.h"

#include "common.h"

// Number of times we randomly probe for old cache record.
// CR: #define WORST_SEARCH_N 10

TranscriptSequence::TranscriptSequence(){//{{{
   // CR: srand(time(NULL));
   M=0;
   cM=0;
   gotGeneNames=false;
   // CR: useCounter = 0;
}//}}}
TranscriptSequence::TranscriptSequence(string fileName, refFormatT format){//{{{
   TranscriptSequence();
   readSequence(fileName,format);
}//}}}
bool TranscriptSequence::readSequence(string fileName, refFormatT format){//{{{
   fastaF.open(fileName.c_str());
   if(!fastaF.is_open()){
      error("TranscriptSequence: problem reading transcript file.\n");
      return false;
   }
   trSeqInfoT newTr;
   // CR: newTr.lastUse=0;
   // CR: newTr.cache=-1;
   string trDesc,geneName;
   long pos;
   istringstream geneDesc;
   trNames.clear();
   geneNames.clear();
   gotGeneNames = true;
   // Record trNames only from gencode ref.
   gotTrNames = (format == GENCODE);
   while(fastaF.good()){
      while((fastaF.peek()!='>')&&(fastaF.good()))
         fastaF.ignore(1000,'\n');
      if(! fastaF.good())break;
      // Read description line:
      getline(fastaF, trDesc, '\n');
      // look for gene name if previous lines had gene name:
      if(gotGeneNames){
         if(format == GENCODE){
            vector<string> lineTokens = ns_misc::tokenize(trDesc,"|");
            if(lineTokens.size()>1){
               geneNames.push_back(lineTokens[1]);
               trNames.push_back(lineTokens[0].substr(1));
            }else{
               gotGeneNames = false;
               gotTrNames = false;
            }
         }else{ // format == STANDARD
            pos=min(trDesc.find("gene:"),trDesc.find("gene="));
            if(pos!=(long)string::npos){
               geneDesc.clear();
               geneDesc.str(trDesc.substr(pos+5));
               geneDesc >> geneName;
               geneNames.push_back(geneName);
            }else{
               gotGeneNames = false;
            }
         }
      }
      // remember position:
      newTr.seek=fastaF.tellg();
      trs.push_back(newTr);
   }
   // Exit if there was an error while reading the file.
   if(fastaF.bad()){
      error("TranscriptSequence: problem reading file.\n");
      return false;
   }
   M = trs.size();
   // Allocate cache for all.
   cache.resize(M);
   //cache.resize(min(M,(long)TRS_CACHE_MAX));
   //cachedTrs.resize(min(M,(long)TRS_CACHE_MAX));
   // Clear eof flag from input stream.
   fastaF.clear();
   return loadSequence();
}//}}}
bool TranscriptSequence::loadSequence(){//{{{
   cache.resize(M);
   string seqLine;
   for(long tr=0;tr<M;tr++){
      // Set input stream to transcript's position.
      fastaF.seekg(trs[tr].seek);
      // Read line by line until reaching EOF or next header line '>'.
      while((fastaF.peek()!='>')&&( getline(fastaF,seqLine,'\n').good())){
         cache[tr]+=seqLine;
      }
      if(fastaF.bad()){
         error("TranscriptSequence: Failed reading transcript %ld\n",tr);
         return false;
      }
      // Clear flags (just in case).
      fastaF.clear();
   }
   return true;
}//}}}
long TranscriptSequence::getG() const{//{{{
   if(!gotGeneNames)return 0;
   return (set<string>(geneNames.begin(),geneNames.end())).size();
}//}}}
const string &TranscriptSequence::getTr(long tr) const{//{{{
   if((tr<0)||(tr>=M))return noneTr;
   // Return pointer to the sequence in cache.
   return cache[tr];
   /* Used with cacheing. {{{
   // Update last use info.
   trs[tr].lastUse = useCounter++;
   return cache[acquireSequence(tr)];
   }}} */
}//}}}
string TranscriptSequence::getSeq(long trI,long start,long l,bool doReverse) const{//{{{
   // Return empty string for unknown transcript.
   if((trI<0)||(trI>=M))return "";
   /* Used with cacheing. {{{
   // Update last use info.
   trs[tr].lastUse = useCounter++;
   // Get position within cache.
   long trI = acquireSequence(tr);
   }}} */
   
   // If position is not within the sequence, return Ns.
   if(start>=(long)cache[trI].size())return string(l,'N');

   string ret;
   // Copy appropriate sequence, fill up the rest with Ns.
   if(start<0){
      ret.assign(-start,'N');
      ret+=cache[trI].substr(0,l+start);
   }else{
      ret = cache[trI].substr(start,l);
      if(((long)ret.size()) < l)ret.append(l-ret.size(), 'N');
   }

   if(!doReverse){
      return ret;
   }else{
      // For reverse return reversed string with complemented bases.
      reverse(ret.begin(),ret.end());
      for(long i=0;i<l;i++)
         if((ret[i]=='A')||(ret[i]=='a'))ret[i]='T';
         else if((ret[i]=='T')||(ret[i]=='t'))ret[i]='A';
         else if((ret[i]=='C')||(ret[i]=='c'))ret[i]='G';
         else if((ret[i]=='G')||(ret[i]=='g'))ret[i]='C';
      return ret;
   }
}//}}}
/* long TranscriptSequence::acquireSequence(long tr){//{{{
   // If the sequence is stored in cache then just return it's cache index.
   if(trs[tr].cache!=-1)return trs[tr].cache;
   long i,newP,j;
   // See if cache is full.
   if(cM<TRS_CACHE_MAX){
      // If cache limit not reached, just add new sequence.
      newP=cM;
      cM++;
   }else{
      // If cache is full, look at WORST_SEARCH_N positions and choose the one least used.
      newP=rand()%cM;
      for(i=0;i<WORST_SEARCH_N;i++){
         j=rand()%cM;
         if(trs[cachedTrs[newP]].lastUse > trs[cachedTrs[j]].lastUse)newP=j;
      }
      // "remove" the transcript from position newP from cache.
      trs[cachedTrs[newP]].cache=-1;
      cache[newP].clear();
   }
   // Set input stream to transcript's position.
   fastaF.seekg(trs[tr].seek);
   string seqLine;
   // Read line by line until reaching EOF or next header line '>'.
   while((fastaF.peek()!='>')&&( getline(fastaF,seqLine,'\n').good())){
      cache[newP]+=seqLine;
   }
   if(fastaF.bad()){
      error("TranscriptSequence: Failed reading transcript %ld\n",tr);
      return 0;
   }
   // Clear flags.
   fastaF.clear();
   // Update cache information.
   cachedTrs[newP]=tr;
   trs[tr].cache=newP;
   // Return transcripts index within cache.
   return newP;
}//}}} */